Faster Self-Organizing Fuzzy Neural Network Training and Improved Autonomy with Time-Delayed Synapses for Locally Recurrent Learning
نویسندگان
چکیده
This chapter describes a number of modifications to the learning algorithm and architecture of the selforganizing fuzzy neural network (SOFNN) to improve its computational efficiency and learning ability. To improve the SOFNN’s computational efficiency, a new method of checking the network structure after it has been modified is proposed. Instead of testing the entire structure every time it has been modified, a record is kept of each neuron’s firing strength for all data previously clustered by the network. This record is updated as training progresses and is used to reduce the computational load of checking network structure changes, to ensure performance degradation does not occur, resulting in significantly reduced training times. It is shown that the modified SOFNN compares favorably to other evolving fuzzy systems in terms of accuracy and structural complexity. In addition, a new architecture of the SOFNN is proposed where recurrent feedback connections are added to neurons in layer three of the structure. Recurrent connections allow the network to learn the temporal information from data and, in contrast to pure feed forward architectures which exhibit static input-output behavior in advance, recurrent models are able to store information from the past (e.g., past measurements of the time-series) and are therefore better suited to analyzing dynamic systems. Each recurrent feedback connection includes a weight which must be learned. In this work a learning approach is proposed where the recurrent feedback weight is
منابع مشابه
An Improved Fuzzy Neural Network for Solving Uncertainty in Pattern Classification and Identification
Dealing with uncertainty is one of the most critical problems in complicatedpattern recognition subjects. In this paper, we modify the structure of a useful UnsupervisedFuzzy Neural Network (UFNN) of Kwan and Cai, and compose a new FNN with 6 types offuzzy neurons and its associated self organizing supervised learning algorithm. Thisimproved five-layer feed forward Supervised Fuzzy Neural Netwo...
متن کاملA recurrent self-organizing neural fuzzy inference network
A recurrent self-organizing neural fuzzy inference network (RSONFIN) is proposed in this paper. The RSONFIN is inherently a recurrent multilayered connectionist network for realizing the basic elements and functions of dynamic fuzzy inference, and may be considered to be constructed from a series of dynamic fuzzy rules. The temporal relations embedded in the network are built by adding some fee...
متن کاملCasual BackPropagation Through Time for Locally Recurrent Neural Networks
This paper concerns dynamic neural networks for signal processing: architectural issues are considered but the paper focuses on learning algorithms that work on-line. Locally recurrent neural networks, namely MLP with IIR synapses and generalization of Local Feedback MultiLayered Networks (LF MLN), are compared to more traditional neural networks, i.e. static MLP with input and/or output buffer...
متن کاملCausal Back Propagation through Time for Locally Recurrent Neural Networks
This paper concerns dynamic neural networks for signal processing: architectural issues are considered but the paper focuses on learning algorithms that work on-line. Locally recurrent neural networks, namely MLP with IIR synapses and generalization of Local Feedback MultiLayered Networks (LF MLN), are compared to more traditional neural networks, i.e. static MLP with input and/or output buffer...
متن کاملA Modfied Self-organizing Map Neural Network to Recognize Multi-font Printed Persian Numerals (RESEARCH NOTE)
This paper proposes a new method to distinguish the printed digits, regardless of font and size, using neural networks.Unlike our proposed method, existing neural network based techniques are only able to recognize the trained fonts. These methods need a large database containing digits in various fonts. New fonts are often introduced to the public, which may not be truly recognized by the Opti...
متن کامل